Epoch: 0001 train_loss= 1.39426 train_acc= 0.25978 val_loss= 1.39960 val_acc= 0.14286 time= 0.81255
Epoch: 0002 train_loss= 1.39037 train_acc= 0.26117 val_loss= 1.40065 val_acc= 0.14286 time= 0.00000
Epoch: 0003 train_loss= 1.38876 train_acc= 0.25978 val_loss= 1.40175 val_acc= 0.14286 time= 0.01563
Epoch: 0004 train_loss= 1.38619 train_acc= 0.25978 val_loss= 1.40294 val_acc= 0.14286 time= 0.00000
Epoch: 0005 train_loss= 1.38400 train_acc= 0.26397 val_loss= 1.40417 val_acc= 0.14286 time= 0.01563
Epoch: 0006 train_loss= 1.38303 train_acc= 0.28911 val_loss= 1.40546 val_acc= 0.10714 time= 0.00000
Epoch: 0007 train_loss= 1.38058 train_acc= 0.29469 val_loss= 1.40678 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.37922 train_acc= 0.31145 val_loss= 1.40817 val_acc= 0.25000 time= 0.00000
Epoch: 0009 train_loss= 1.37627 train_acc= 0.30587 val_loss= 1.40961 val_acc= 0.25000 time= 0.00000
Epoch: 0010 train_loss= 1.37676 train_acc= 0.31285 val_loss= 1.41137 val_acc= 0.25000 time= 0.01563
Epoch: 0011 train_loss= 1.37469 train_acc= 0.31145 val_loss= 1.41340 val_acc= 0.25000 time= 0.00000
Epoch: 0012 train_loss= 1.37418 train_acc= 0.31145 val_loss= 1.41561 val_acc= 0.25000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38164 accuracy= 0.30088 time= 0.00000 
